Today's fast-moving world sees an abundance of image data in everyday life. From messages to insurance claims to even judicial systems, image data plays a pivotal role in facilitating several critical Big Data applications. Some of these applications such as automatic license plate recognition (ALPR) use CCTV cameras to capture snapshots of traffic from real-time video, inadvertently resulting in the generation vast amounts of image data on a daily basis. This brings with it the herculean task of processing these images to extract the essential information as efficiently as possible. The conventional method of processing images in a sequential manner can be very time consuming on account of the vast multitude of images and the intensive computation involved in order to process these. Distributed image processing seeks to provide a solution to this problem by splitting the computations involved across multiple nodes. This paper presents a novel framework to implement distributed image processing via OpenCV on HPCC Systems distributed node architecture*, a set of high-performance computing clusters. The proposed approach when tested on the Indian License Plates Dataset was found to be 85 percent accurate. Additionally, a 30 percent decrease in computation time was observed when executed on a multi-node setup without any impact to accuracy.