Region tracking becomes a challenging problem at the presence of low contrast and textured images such as cilia video images where beating cilia appear as moving texture. Tracking such patterns requires extracting of features that are capable of discriminating them effectively. In this paper, a method based on texture features for region tracking is proposed. The texture features are extracted from a sequence of images using Gaussian Markov Random Fields (GMRF). These features are employed to track the motion of a given region and extract its trajectory. The proposed method is evaluated on synthetic samples generated for this purpose and demonstrates good tracking performance depending only on texture features. Our proposed method is successfully utilized to extract the trajectory of the cilia motion which could help to analyze the beating behavior of cilia.