Distinguishing cysts from other tumors is a routine clinical practice for diagnosing breast cancer. It has shown that more accurate diagnosis can be achieved by combining elasticity images with traditional B-mode ultrasound images. In this paper, we propose a fully automatic system to detect cysts jointly in both B-mode and elasticity images. It is based on database-guided techniques that learn the knowledge of cyst appearance automatically from B-mode and elasticity images in a database. Further, for a detected cyst in a query image, the cysts with similar image appearance in the database are retrieved to improve diagnostic accuracy and confidence. In the experiment, we show that our system achieves high sensitivity and specificity in cyst diagnosis.