We introduce a novel method for nonrigid image registration which combines the total variation filter and a fourth-order filter. We decompose the deformation field into two components, that is, a piecewise constant component and a smooth component. The total variation filter is used for the first component and the fourth-order filter is used for the second one. Then, we present a new PDE-based image registration model suitable for both smooth and nonsmooth deformation problem. Meanwhile, the local-global similarity measure is used in our method to improve the accuracy and robustness for image matching. By applying the split Bregman algorithm and dual algorithm, we present a fast and stable numerical scheme. The numerical experiments and comparisons on both synthetic images and real images demonstrate the effectiveness of our method in nonrigid image registration.