Early detection and treatment of breast cancer can effectively prohibit its progress and decrease mortality rate. Recently, ultrasound imaging plays an important role in the field of breast cancer diagnosis because of its convenience and non-invasive. With the assist of computer-aided diagnosis (CAD) system, the characteristics of tumor can be detected and provided to physicians as a critical reference. Because the shape of a tumor may be altered due to the stress caused by the ultrasound probe, the registration method can be utilized to analyze the variation of tumor between pre- and post-compression. Therefore, we can determine whether the tumor is benign or not with several statistical materials. The experimental results will show that this proposed model can efficaciously detect the tumors and support the clinical diagnoses.