Virtual reality technology is an attractive means for medical simulations and treatment, especially for patients with cancer. The overall goal of this research is to introduce a conceptual virtual environment with real-world dynamic contents to develop an effective breathing exercise tool that will aid in regulating breathing movements and eventually increase the oxygen intake of users/patients. This study focuses on an essential component of the virtual reality therapy framework. The work introduces a novel automated approach towards computing the lung capacity. The overall objective is to aid lung cancer patients, or those with breathing disorders regulate their breath through real-time analysis of respiration movements using a smart-phone. Traditionally, lung cancer patients and those with certain breathing disorders use a spirometer device to measure their lung capacity. However, accurate measurements using the spirometer requires some sort of training and adjustment, which may be difficult for certain groups of patients, especially the elderly. In this paper, a methodology is proposed to process the recorded acoustic signal of respiration using a microphone, and a model is introduced to estimate the lung size with a high degree of accuracy. To estimate the lung capacity, Voice-Activity-Detection (VAD) is fine-tuned and applied to the acoustic signal of respiration to split the signal into voice and silence phases. The average time duration and energy of the breathing phases (inhale and exhale voice phases) are computed to derive the lung capacity. The signal processing relies on accurate signal segmentation and signal energy computation of the breathing cycles. This model of using a microphone and the acoustic signal of respiration to estimate lung capacity yields a high degree of accuracy, exceeding 85%. In the framework, lung capacity is computed simultaneously as the patient is breathing in real time. Consequently, the patient will be motivated to take the next coming breath deeply if the previous one was not sufficient, thus, virtually regulating his/her own breath. The results indicate that the proposed model is highly accurate and effective for estimating lung capacity. The potential outcome of this research is that the intended virtual reality framework, if fully implemented and integrated with a high quality animated application on a smart-phone, would directly aid individuals, especially lung cancer patients, regulate their breath by having a daily basis estimate of their lung size using a hand-held device at home.