This paper investigates the problem of atlas registration of brain images with tumors. Multi-parametric imaging modalities are first utilized for segmentations of different tissues, and to compute the posterior probability map (PBM) of membership to each tissue class, using supervised learning. Similar maps are generated in the initially normal atlas, by modeling the tumor growth. An Expectation-Maximization algorithm is used to estimate the spatial transformation and other parameters related to tumor simulation are optimized through Asynchronous Parallel Pattern Search (APPSPACK). The proposed method has been evaluated on simulated data sets created by Statistically Simulated Deformations (SSD), and real multichannel Glioma data sets. The performance has been evaluated both quantitatively and qualitatively. The results show that our method is promising to achieve a good similarity between the warped templates and patient images.