Lossless image compression is in high demand in medical image applications. With the development of General Purpose Graphic Processing Unit (GPGPU) computing techniques, sequential lossless image compression algorithms can be modified to achieve more efficiency and speed. In this paper, a novel adaptation of Computation Unified Device Architecture (CUDA) to a wavelet tree based image compression algorithm is presented. Both transform phase and encoding phase of the compression algorithm have been redesigned for parallelization and efficiency. Our algorithm performs faster than the lossless JPEG-XR algorithm, with comparable compression ratios. Further improvements in speed and flexibility are also under current investigation.