People who perform work on micro-task crowdsourcing platforms, often do so using a mouse and/or keyboard for many hours at a time, while alternative modes of input could potentially provide a better experience. This research investigates the feasibility of using webcam-based eye-tracking in a micro-task work environment. We accomplish this by setting up a user study (n = 20), where participants are asked to perform a series of image classification tasks using either a mouse or just their eyes. Overall, results show that participants using a webcam are generally able to complete the tasks adequately. However, they perform somewhat slower and less accurate, and are less content with their overall experience. Based on our results, we suggest that there are still limitations to overcome when applying webcam-based eye-tracking to micro-tasks.