This document proposes a low-complexity K-means clustering architecture using a Coordinate Rotation Digital Computer-based engine to efficiently compute Euclidean distances between data points and centroids. The architecture was synthesized using a 130nm process and estimated to have a core area of 0.36 mm^2 and power consumption of 9.21 mW at 100 MHz, making it suitable for real-time low-power applications like mobile health monitoring. The proposed design was analyzed using ModelSim and Xilinx ISE software.